Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 7272
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Men
    -0.78
     T
    -0.78
    s
    -0.78
     C
    -0.77
     
    -0.76
    -
    -0.75
     Te
    -0.75
     K
    -0.74
     \
    -0.74
     P
    -0.73
    POSITIVE LOGITS
     myſelf
    1.50
    ſelves
    1.45
     iſt
    1.42
     Jefus
    1.36
     themſelves
    1.32
     pleaſure
    1.32
     raiſ
    1.29
     purpoſe
    1.27
    ſelf
    1.26
     ་་
    1.26
    Activations Density 0.505%

    No Known Activations